Topic Models for Dynamic Translation Model Adaptation.
ACL '12: Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Short Papers - Volume 2(2012)
摘要
We propose an approach that biases machine translation systems toward relevant translations based on topic-specific contexts, where topics are induced in an unsupervised way using topic models; this can be thought of as inducing subcorpora for adaptation without any human annotation. We use these topic distributions to compute topic-dependent lexical weighting probabilities and directly incorporate them into our translation model as features. Conditioning lexical probabilities on the topic biases translations toward topic-relevant output, resulting in significant improvements of up to 1 BLEU and 3 TER on Chinese to English translation over a strong baseline.
更多查看译文
关键词
English translation,biases machine translation system,relevant translation,topic biases translation,topic distribution,topic model,translation model,conditioning lexical probability,topic-dependent lexical weighting probability,human annotation,dynamic translation model adaptation
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络